Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks.

Maan Qraitem Nazia Tasnim Kate Saenko Bryan A. Plummer

Published in: CoRR (2024)

Keyphrases

vision system
computer vision
countermeasures
neural network
automatically generated
security threats
terrorist attacks
data sets
databases
data mining
learning algorithm
image processing
high level
smart card
generation process
active vision